INDEX

Explanations

officially

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Â©

-0.28

pector

-0.27

ital

-0.27

-cur

-0.27

 dece

-0.26

mouth

-0.26

Ãł

-0.26

å¼ı

-0.25

çķĻ

-0.25

 excer

-0.25

POSITIVE LOGITS

 became

0.31

æĪĲä¸ºä¸ĢåĲį

0.31

æĪĲä¸º

0.28

ä¹ŁæĪĲä¸º

0.27

æĪĲä¸ºä¸Ģä¸ª

0.26

IDES

0.26

ERY

0.26

 becomes

0.25

 recognized

0.25

æĪĲä¸ºäºĨ

0.25

Activations Density 0.011%

officially

No Comments

No Known Activations